Utforskan av Feature Extraction för händelsespårning inom Beach Volleyboll : Spatiotemporal Feature Extraction med hjälp av Human Pose Estimation

This study explores extracting features from Beach Volleyball video data using Human Pose Estimation models and evaluating the features by training and assessing a Machine Learning model with the aforementioned features. The methodology of the study consists of a literature study, interviews, pre-experiments to help decide on a pipeline and, extracting and evaluating features. The results of the study show that the models trained on the extraced features did not generalise well on unseen data. This could be due to the training dataset being too small for the choice of ML model orthe choice of evaluation method.